首页
新闻动态
通知公告
通知公告  
特邀美国天普大学张凯副教授来校作学术报告

报告题目:Mining big data with recapitulated randomness

报告时间:820日(周二)上午1030

报告地点:学科3号楼N301

报告人:张凯 副教授

主持人:刘青山 教授

欢迎广大师生踊跃参加!


江苏省大数据分析技术重点实验室

江苏省气象能源利用与控制工程技术研究中心

江苏省大气环境与装备技术协同创新中心

自动化学院

2019819



报告摘要:Matrix low-rank decomposition plays a fundamental role in modern scientific computing and optimization algorithms. Randomized algorithms recently received tremendous amount of interest in computing partial approximate factorization with theoretic performance guarantees. However, the need to manipulate the entire input matrix still imposes severe memory and computational bottlenecks. In this talk we find an interesting underlying relation between matrix sketching and lossy data compression, based on which a cascaded bilateral sampling framework is devised to sketch an $m\times n$ matrix in only $\O{(m+n)}$ time and space. The proposed frame accesses only a small number of matrix rows and columns, which significantly improves the memory footprint. Meanwhile, by sequentially teaming two rounds of sketching procedures and upgrading the sampling strategy from uniform sampling to more sophisticated, encoding-orientated clustering, significant algorithmic boosting is achieved to uncover more granular structures in the data. Empirical results on numerical simulations and a wide spectrum of real-world, large-scale problems in unsupervised, semi-supervised, and transfer learning problems demonstrate the power of the proposed framework in terms of both efficiency and accuracies.

报告人简介:张凯,现任美国天普大学计算机系副教授。中国科学院自动化所硕士,于2008年获得香港科技大学博士学位。先后就职于美国伯克利国家实验室、西门子研究院和NEC实验室。主要研究方向为大规模机器学习和数据挖掘算法,以及在复杂网络,时间序列分析,商业智能领域的应用。在ICML, NIPSKDDAAAITNNTKDE等顶级计算机会议及期刊发表论文四十余篇。获得2016 年国际数据挖掘会议 ACM SIGKDD 最佳论文提名奖,在脑功能网络的工作被著名国际期刊Brain 选为杂志封面(20168)并由麦克阿瑟奖得主Basseet撰文评论(The Flexible Brain)


江苏省气象能源利用与控制工程技术研究中心 NUIST备80151 版权所有 Copyright © 2015 All right reserved

地址:南京市宁六路219号 邮编:210044

备案号:NUIST备80151